dogfood_reload

SERVERYaver SOURCEyaver-cli

High RISK CLASS

Category Execute

Parameters 92 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/dogfood-reload.md

WHAT IT DOES

What dogfood_reload does on Yaver

AI agents invoke dogfood_reload to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`lane`	string	Yes	Render lane selected in Dogfood Settings.
`mode`	string	—	Reload strength. Hermes always produces a fresh bundle for correctness.
`platform`	string	—	Optional ios or android hint for Hermes builds.
`bundle_id`	string	—	Optional iOS/Android application identifier.
`device_id`	string	—	Optional owned remote box that builds/renders the app. Empty means this machine.
`project_name`	string	—	App project name for display and native bundle identity.
`project_path`	string	Yes	Exact selected checkout on the render box. Its current working tree is rendered without any Git mutation.
`target_device_id`	string	—	Optional exact connected app/phone session. When set, delivery fails closed instead of broadcasting.
`runtime_session_id`	string	—	Required for the WebRTC remote-runtime lane.

Parameters from the server's own tool schema.

RISK

Why dogfood_reload is rated High

Triggers an app reload/render on an external runtime device without modifying data.

From the tool's definition Reload the exact app checkout selected for Dogfood, using its browser, Hermes, or remote-runtime lane

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs dogfood_reload safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dogfood_reload, this is the rule to start with:

dogfood_reload Rate-limited

dogfood_reload stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "dogfood_reload": {
      "limits": [
        {
          "counter": "dogfood_reload_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every dogfood_reload call is checked against it from then on.

FAQ

Questions about dogfood_reload

What does the dogfood_reload tool do? +

Reload the exact app checkout selected for Dogfood, using its browser, Hermes, or remote-runtime lane. This renders the current working tree (commonly a solo developer's main branch) and never commits, checks out, rebases, pulls, or pushes Git. Pass device_id for the render box; project_path is strongly preferred so another active project can never be reloaded by accident. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does dogfood_reload accept? +

dogfood_reload accepts 9 parameters: lane, mode, platform, bundle_id, device_id, project_name, project_path, target_device_id, runtime_session_id. Required: lane, project_path. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on dogfood_reload? +

Register the Yaver MCP server in PolicyLayer and add a rule for dogfood_reload: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.

What risk level is dogfood_reload? +

dogfood_reload is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit dogfood_reload? +

Yes. Add a rate_limit block to the dogfood_reload rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block dogfood_reload completely? +

Set action: deny in the PolicyLayer policy for dogfood_reload. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides dogfood_reload? +

dogfood_reload is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 678 Yaver tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →